Security audit

Tvs Verify

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a disclosed checklist for verifying recent AI-made changes and does not add hidden execution, persistence, credential access, or destructive behavior.

Installers should understand this is a Chinese-language verification workflow. It may prompt the agent to run targeted tests, lint, builds, browser checks, or read changed files when verifying a recent fix, but the artifact tells the agent to keep checks narrow and not modify source during verification.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The skill description contains broad, everyday phrases like '验证、确认、测试、证明、检查是否完成' that can match many routine user requests, increasing the chance the skill is invoked outside its intended narrow verification scope. Over-broad triggering can cause the agent to adopt this skill when the user did not explicitly ask for post-change verification, leading to inappropriate workflow steering and reduced safety if verification guidance is applied in the wrong context.

Natural-Language Policy Violations

Medium

Confidence: 98% confidence
Finding: The skill is written entirely in Chinese and implicitly constrains behavior to Chinese without stating a justified locale restriction or allowing response-language selection. In multilingual environments this can cause the agent to switch languages unexpectedly, misunderstand user intent, or produce unusable outputs, which is a prompt-quality and reliability risk rather than a direct code-execution issue.

Static analysis

No suspicious patterns detected.